Models

Query the model catalog programmatically through the OpenAI-compatible models API, served from https://api.akashml.com/v1. Use it to discover the model IDs available to your account before sending inference requests.

Each entry also carries its current rates: pricing.input_cache_read for input tokens served from a prompt cache hit, and discount_to_user while a promotion is running. See How pricing is calculated for the formulas.